dev → main: rule usage telemetry, the plugin's derived version, and the backlog since b267037 #136

Merged
bvandeusen merged 19 commits from dev into main 2026-09-02 18:52:20 -04:00
Showing only changes of commit 70761b16d9 - Show all commits
+39 -5
View File
@@ -16,7 +16,7 @@ from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from tests.helpers import fake_rule
from tests.helpers import fake_note, fake_rule
# The MCP tool layer reads its caller from a ContextVar the HTTP transport sets
# per request; a unit test has no request, so it binds the caller itself. The
@@ -33,14 +33,30 @@ pytestmark = pytest.mark.usefixtures("_bind_user")
# each of these does.
def _arm_patches(pc, hits, recorder):
# The write-path hint returns early when a write matched nothing at all — no
# staleness, no synced record, no prior-art menu, no shape signal. The rule arm
# sits deliberately on the FAR side of that guard, because it runs a semantic
# search and moving it above would mean an embedding query on every write in
# the session (#3311's closing note, and the reason its gating is a separate
# question from precision).
#
# So a fixture that stubs every other arm to empty never reaches the rule arm
# at all — which is what the first run of this file did. The note hit below is
# not decoration: it is the condition the arm requires in order to fire.
_PRIOR_ART = [(0.72, fake_note(id=9, title="debounce helper", user_id=1,
note_type="snippet"))]
def _arm_patches(pc, hits, recorder, prior_art=None):
"""The minimum stubbing that lets the rule arm run and nothing else."""
return (
patch.object(pc, "get_writepath_config",
AsyncMock(return_value={"enabled": True, "threshold": 0.6,
"top_k": 3})),
patch.object(pc.snippets_svc, "list_snippets", AsyncMock(return_value=([], 0))),
patch.object(pc, "semantic_search_notes", AsyncMock(return_value=[])),
patch.object(pc, "semantic_search_notes",
AsyncMock(return_value=_PRIOR_ART if prior_art is None
else prior_art)),
patch.object(pc, "semantic_search_rules", AsyncMock(return_value=hits)),
patch.object(pc, "record_retrieval", MagicMock()),
patch.object(pc, "record_surfaced", MagicMock()),
@@ -50,10 +66,10 @@ def _arm_patches(pc, hits, recorder):
)
async def _run_arm(hits, recorder, **kwargs):
async def _run_arm(hits, recorder, prior_art=None, **kwargs):
from scribe.services import plugin_context as pc
with ExitStack() as stack:
for ctx in _arm_patches(pc, hits, recorder):
for ctx in _arm_patches(pc, hits, recorder, prior_art):
stack.enter_context(ctx)
return await pc.build_write_path_hint(
1, "frontend/src/api/client.ts", code="x" * 400, **kwargs
@@ -106,6 +122,24 @@ async def test_nothing_is_recorded_when_every_hit_was_already_held():
assert rec.call_count == 0
@pytest.mark.asyncio
async def test_the_arm_does_not_fire_on_a_write_that_matched_nothing():
"""The gate, pinned — because the fixture above now depends on it and a
silent change would make every other test here pass vacuously.
A write matching no prior art returns before the rule arm runs. That is
deliberate: the arm is a semantic search, and ungating it means an
embedding query on every write in the session. #3311 is explicit that the
gate stays until the arm's precision is fixed, so this failing is a signal
to go read that issue rather than to update the assertion.
"""
rec = MagicMock()
hits = [(0.71, fake_rule(id=156, title="A wait with no deadline is a bug"))]
await _run_arm(hits, rec, prior_art=[])
assert rec.call_count == 0
@pytest.mark.asyncio
async def test_a_failing_recorder_does_not_break_the_write():
"""Telemetry must never take down the surface it observes. The arm is